Continual Test-Time Unsupervised Domain Adaptation

Continual test-time domain adaptation (TTA) is a challenging topic in the field of source-free domain adaptation, which focuses on addressing cross-domain data during inference with a continuously changing data distribution. Previous methods have been found to lack noise robustness, leading to a significant increase in errors under strong noise. In this chapter, we address the noise robustness problem in continual TTA by offering three effective recipes to mitigate it. At the category level, we employ the Taylor cross-entropy loss to alleviate the low confidence category bias commonly associated with cross-entropy. At the sample level, we reweight the target samples based on uncertainty to prevent the model from overfitting on noisy samples. Finally, to reduce pseudo-label noise, we propose a soft ensemble negative learning mechanism to guide the model optimization using ensemble complementary pseudo-labels. Our method achieves state-of-the-art performance on three widely used continual TTA datasets, particularly in the strong noise setting that we introduced.